Max Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Max Yang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Nathan F. Lepora
University of Bristol
5 shared publications - Yijiong Lin
Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K.
4 shared publications - Chenghua Lu
Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K.
3 shared publications - Haoran Li
School of Robotics, Xian Jiaotong-Liverpool University, Suzhou, China
3 shared publications - Alex Church
Department of Engineering Mathematics and Bristol Robotics Laboratory, University of Bristol, Bristol, U.K.
2 shared publications Bowen Deng
Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K.
2 shared publications
Latest Publications
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. PP (10834435) , 1-12
NeuralTouch: Neural Descriptors for Precise Sim-to-Real Tactile Robot Control
Grasping accuracy is a critical prerequisite for precise object manipulation that may require careful alignment between the robot hand and an object. Neural descriptor fields (NDFs) offer a promising vision-based method to generate grasping poses that generalize across object categories. However, NDFs alone can produce inaccurate poses due to imperfect camera calibration, incomplete point clouds, and object variability. Alternatively, tactile sensing enables more precise contact, but existing approaches limit policies to simple predefined contact geometries. In this work, we introduce NeuralTouch, a multimodal framework that integrates NDFs and tactile sensing to enable accurate generalizable grasping through gentle physical interaction. Our approach leverages NDFs to implicitly represent the target contact geometry, from which a deep reinforcement learning policy is trained to refine the grasp using tactile feedback. This policy is conditioned on the neural descriptors and does not require explicit specification of contact types. We validate NeuralTouch through ablation studies in simulation and with zero-shot transfer to real-world manipulation tasks, such as peg-out/in-hole and bottle lid opening. Our results show that NeuralTouch significantly improves grasping accuracy and robustness over baseline methods, offering a general framework for precise, contact-rich robotic grasp-based manipulation.
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. PP (10834435) , 1-12
NeuralTouch: Neural Descriptors for Precise Sim-to-Real Tactile Robot Control
Grasping accuracy is a critical prerequisite for precise object manipulation that may require careful alignment between the robot hand and an object. Neural descriptor fields (NDFs) offer a promising vision-based method to generate grasping poses that generalize across object categories. However, NDFs alone can produce inaccurate poses due to imperfect camera calibration, incomplete point clouds, and object variability. Alternatively, tactile sensing enables more precise contact, but existing approaches limit policies to simple predefined contact geometries. In this work, we introduce NeuralTouch, a multimodal framework that integrates NDFs and tactile sensing to enable accurate generalizable grasping through gentle physical interaction. Our approach leverages NDFs to implicitly represent the target contact geometry, from which a deep reinforcement learning policy is trained to refine the grasp using tactile feedback. This policy is conditioned on the neural descriptors and does not require explicit specification of contact types. We validate NeuralTouch through ablation studies in simulation and with zero-shot transfer to real-world manipulation tasks, such as peg-out/in-hole and bottle lid opening. Our results show that NeuralTouch significantly improves grasping accuracy and robustness over baseline methods, offering a general framework for precise, contact-rich robotic grasp-based manipulation.
- 21 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (19) , 35672-35686
Classification of Vision-Based Tactile Sensors: A Review
Vision-based tactile sensors (VBTS) have gained widespread application in robotic hands, grippers and prosthetics due to their high spatial resolution, low manufacturing costs, and ease of customization. While VBTSs have common design features, such as a camera module, they can differ in a rich diversity of sensing principles, material compositions, multimodal approaches, and data interpretation methods. Here, we propose a novel classification of VBTS that categorizes the technology into two primary sensing principles based on the underlying transduction of contact into a tactile image: the Marker-Based Transduction Principle and the Intensity-Based Transduction Principle. Marker-Based Transduction interprets tactile information by detecting marker displacement and changes in marker density. In contrast, Intensity-Based Transduction maps external disturbances with variations in pixel values. Depending on the design of the contact module, Marker-Based Transduction can be further divided into two subtypes: Simple Marker-Based (SMB) and Morphological Marker-Based (MMB) mechanisms. Similarly, the Intensity-Based Transduction Principle encompasses the Reflective Layer-based (RLB) and Transparent Layer-Based (TLB) mechanisms. This paper provides a comparative study of the hardware characteristics of these four types of sensors including various combination types, and discusses the commonly used methods for interpreting tactile information. This comparison reveals some current challenges faced by VBTS technology and directions for future research.
- 21 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (19) , 35672-35686
Classification of Vision-Based Tactile Sensors: A Review
Vision-based tactile sensors (VBTS) have gained widespread application in robotic hands, grippers and prosthetics due to their high spatial resolution, low manufacturing costs, and ease of customization. While VBTSs have common design features, such as a camera module, they can differ in a rich diversity of sensing principles, material compositions, multimodal approaches, and data interpretation methods. Here, we propose a novel classification of VBTS that categorizes the technology into two primary sensing principles based on the underlying transduction of contact into a tactile image: the Marker-Based Transduction Principle and the Intensity-Based Transduction Principle. Marker-Based Transduction interprets tactile information by detecting marker displacement and changes in marker density. In contrast, Intensity-Based Transduction maps external disturbances with variations in pixel values. Depending on the design of the contact module, Marker-Based Transduction can be further divided into two subtypes: Simple Marker-Based (SMB) and Morphological Marker-Based (MMB) mechanisms. Similarly, the Intensity-Based Transduction Principle encompasses the Reflective Layer-based (RLB) and Transparent Layer-Based (TLB) mechanisms. This paper provides a comparative study of the hardware characteristics of these four types of sensors including various combination types, and discusses the commonly used methods for interpreting tactile information. This comparison reveals some current challenges faced by VBTS technology and directions for future research.
- 4 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (2) , 1545-1552
Coarse-to-Fine Robotic Pushing Using Touch, Vision and Proprioception
Robotic pushing can be a complicated process that is indicative of the techniques needed for general object manipulation. Here we propose a novel coarse-to-fine approach that combines visual localization with a pushing strategy using tactile and proprioceptive feedback. In the coarse control stage, visual feedback continuously adjusts the relative pose between the end-effector and the object. This serves as an operational point to start the fine control. In the fine control phase, relative sensor-object pose information from tactile sensing is used to accurately control the end-effector to push the object to the target pose. The visual and tactile feedback are integrated into a multi-stage control process so that the object can be moved to a target position and orientation; in contrast, using only a single-stage pushing method does not permit control of object orientation. Our study confirms that combining tactile and visual approaches is more efficient and accurate for a fairly complex manipulation task. We expect that related methods will extend to more challenging prehensile object manipulation tasks to improve dexterous capabilities of robots.
- 4 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (2) , 1545-1552
Coarse-to-Fine Robotic Pushing Using Touch, Vision and Proprioception
Robotic pushing can be a complicated process that is indicative of the techniques needed for general object manipulation. Here we propose a novel coarse-to-fine approach that combines visual localization with a pushing strategy using tactile and proprioceptive feedback. In the coarse control stage, visual feedback continuously adjusts the relative pose between the end-effector and the object. This serves as an operational point to start the fine control. In the fine control phase, relative sensor-object pose information from tactile sensing is used to accurately control the end-effector to push the object to the target pose. The visual and tactile feedback are integrated into a multi-stage control process so that the object can be moved to a target position and orientation; in contrast, using only a single-stage pushing method does not permit control of object orientation. Our study confirms that combining tactile and visual approaches is more efficient and accurate for a fairly complex manipulation task. We expect that related methods will extend to more challenging prehensile object manipulation tasks to improve dexterous capabilities of robots.
- 19 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 30 (1) , 333-344
DexiTac: Soft Dexterous Tactile Gripping
Grasping objects—whether they are flat, round, or narrow and whether they have regular or irregular shapes—introduces difficulties in determining the ideal grasping posture, even for the most state-of-the-art grippers. In this article, we presented a reconfigurable pneumatic gripper with fingers that could be set in various configurations, such as hooking, supporting, closuring, and pinching. Each finger incorporates a dexterous joint, a rotating joint, and a customized plug-and-play visuotactile sensor, the DigiTac-v1.5, to control manipulation in real time. We propose a tactile kernel density manipulation strategy for simple and versatile control, including detecting grasp stability, responding to disturbances, and guiding dexterous manipulations. We develop a double closed-loop control system that separately focuses on secure grasping and task management, demonstrated with tasks that highlight the previous capabilities. The gripper is relatively easy to fabricate and customize, offering a promising and extensible way to combine soft dexterity and tactile sensing for diverse applications in robotic manipulation.
- 19 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 30 (1) , 333-344
DexiTac: Soft Dexterous Tactile Gripping
Grasping objects—whether they are flat, round, or narrow and whether they have regular or irregular shapes—introduces difficulties in determining the ideal grasping posture, even for the most state-of-the-art grippers. In this article, we presented a reconfigurable pneumatic gripper with fingers that could be set in various configurations, such as hooking, supporting, closuring, and pinching. Each finger incorporates a dexterous joint, a rotating joint, and a customized plug-and-play visuotactile sensor, the DigiTac-v1.5, to control manipulation in real time. We propose a tactile kernel density manipulation strategy for simple and versatile control, including detecting grasp stability, responding to disturbances, and guiding dexterous manipulations. We develop a double closed-loop control system that separately focuses on secure grasping and task management, demonstrated with tasks that highlight the previous capabilities. The gripper is relatively easy to fabricate and customize, offering a promising and extensible way to combine soft dexterity and tactile sensing for diverse applications in robotic manipulation.
- 17 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (9) , 5472-5479
Bi-Touch: Bimanual Tactile Manipulation With Sim-to-Real Deep Reinforcement Learning
Bimanual manipulation with tactile feedback will be key to human-level robot dexterity. However, this topic is less explored than single-arm settings, partly due to the availability of suitable hardware along with the complexity of designing effective controllers for tasks with relatively large state-action spaces. Here we introduce a dual-arm tactile robotic system (Bi-Touch) based on the Tactile Gym 2.0 setup that integrates two affordable industrial-level robot arms with low-cost high-resolution tactile sensors (TacTips). We present a suite of bimanual manipulation tasks tailored towards tactile feedback: bi-pushing, bi-reorienting and bi-gathering. To learn effective policies, we introduce appropriate reward functions for these tasks and propose a novel goal-update mechanism with deep reinforcement learning. We also apply these policies to real-world settings with a tactile sim-to-real approach. Our analysis highlights and addresses some challenges met during the sim-to-real application, e.g. the learned policy tended to squeeze an object in the bi-reorienting task due to the sim-to-real gap. Finally, we demonstrate the generalizability and robustness of this system by experimenting with different unseen objects with applied perturbations in the real world. Code and videos are available at https://sites.google.com/view/bi-touch/ .
- 17 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (9) , 5472-5479
Bi-Touch: Bimanual Tactile Manipulation With Sim-to-Real Deep Reinforcement Learning
Bimanual manipulation with tactile feedback will be key to human-level robot dexterity. However, this topic is less explored than single-arm settings, partly due to the availability of suitable hardware along with the complexity of designing effective controllers for tasks with relatively large state-action spaces. Here we introduce a dual-arm tactile robotic system (Bi-Touch) based on the Tactile Gym 2.0 setup that integrates two affordable industrial-level robot arms with low-cost high-resolution tactile sensors (TacTips). We present a suite of bimanual manipulation tasks tailored towards tactile feedback: bi-pushing, bi-reorienting and bi-gathering. To learn effective policies, we introduce appropriate reward functions for these tasks and propose a novel goal-update mechanism with deep reinforcement learning. We also apply these policies to real-world settings with a tactile sim-to-real approach. Our analysis highlights and addresses some challenges met during the sim-to-real application, e.g. the learned policy tended to squeeze an object in the bi-reorienting task due to the sim-to-real gap. Finally, we demonstrate the generalizability and robustness of this system by experimenting with different unseen objects with applied perturbations in the real world. Code and videos are available at https://sites.google.com/view/bi-touch/ .
- 13 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (9) , 5480-5487
Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing
Object pushing presents a key non-prehensile manipulation problem that is illustrative of more complex robotic manipulation tasks. While deep reinforcement learning (RL) methods have demonstrated impressive learning capabilities using visual input, a lack of tactile sensing limits their capability for fine and reliable control during manipulation. Here we propose a deep RL approach to object pushing using tactile sensing without visual input, namely tactile pushing. We present a goal-conditioned formulation that allows both model-free and model-based RL to obtain accurate policies for pushing an object to a goal. To achieve real-world performance, we adopt a sim-to-real approach. Our results demonstrate that it is possible to train on a single object and a limited sample of goals to produce precise and reliable policies that can generalize to a variety of unseen objects and pushing scenarios without domain randomization. We experiment with the trained agents in harsh pushing conditions, and show that with significantly more training samples, a model-free policy can outperform a model-based planner, generating shorter and more reliable pushing trajectories despite large disturbances. The simplicity of our training environment and effective real-world performance highlights the value of rich tactile information for fine manipulation.
- 13 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (9) , 5480-5487
Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing
Object pushing presents a key non-prehensile manipulation problem that is illustrative of more complex robotic manipulation tasks. While deep reinforcement learning (RL) methods have demonstrated impressive learning capabilities using visual input, a lack of tactile sensing limits their capability for fine and reliable control during manipulation. Here we propose a deep RL approach to object pushing using tactile sensing without visual input, namely tactile pushing. We present a goal-conditioned formulation that allows both model-free and model-based RL to obtain accurate policies for pushing an object to a goal. To achieve real-world performance, we adopt a sim-to-real approach. Our results demonstrate that it is possible to train on a single object and a limited sample of goals to produce precise and reliable policies that can generalize to a variety of unseen objects and pushing scenarios without domain randomization. We experiment with the trained agents in harsh pushing conditions, and show that with significantly more training samples, a model-free policy can outperform a model-based planner, generating shorter and more reliable pushing trajectories despite large disturbances. The simplicity of our training environment and effective real-world performance highlights the value of rich tactile information for fine manipulation.